Falcon: Honest-Majority Maliciously Secure Framework for Private Deep Learning
By Sameer Wagh, Shruti Tople, Fabrice Benhamouda, Eyal Kushilevitz, Prateek Mittal, Tal Rabin. Proceedings on Privacy Enhancing Technologies, 2020
389 citations recorded by the source corpus.
Abstract We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages – (i) It is highly expressive with support for high capacity networks such as VGG16 (ii) it supports batch normalization which is important for training complex networks such as AlexNet (iii) Falcon guarantees security with abort against malicious adversaries, assuming an honest majority (iv) Lastly, Falcon presents new theoretical insights for protocol design that make it highly efficient and allow it to outperform existing secure deep learning solutions. Compared to prior art for private inference, we are about 8× faster than SecureNN (PETS’19) on average and comparable to ABY3 (CCS’18). We are about 16 − 200× more communication efficient than either of these. For private training, we are about 6× faster than SecureNN, 4.4× faster than ABY3 and about 2−60× more communication efficient. Our experiments in the WAN setting show that over large networks and datasets, compute operations dominate the overall latency of MPC, as opposed to the communication.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/926b2495999895300e5ea8aecbfca11a9c8a8e7a
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Awni Y. Hannun
- Jonathan Passerat-Palmbach
- Andrew Trask
- Daniel Rueckert
- L. V. D. van der Maaten
- Shobha Venkataraman
- Shubho Sengupta
- Marcus R. Makowski
Citations in the corpus
- End-to-end privacy preserving deep learning on multi-institutional medical imaging (2021, methodology): “It represents an alternative to protocols like SecureNN 29 or Falcon 41 , and computes private comparisons with a single round of communication.”
- CrypTen: Secure Multi-Party Computation Meets Machine Learning (2021, methodology): “The prospect of such applications of machine learning with rigorous privacy and security guarantees has spurred a number of studies on machine learning via secure MPC [40, 43, 50, 62, 67, 71, 72].”